Audio Transcription with Sber Salute Speech

Transcribe audio/video files to text with timestamps via Salute Speech async REST API.

Requirements

• API Key: Environment variable SALUTE_AUTH_DATA must be set (Base64-encoded client_id:client_secret or raw authorization key from https://developers.sber.ru/studio/).
• SSL note: The script disables SSL verification by default (verify_ssl=False) because Sber's certificate chain is non-standard. This is expected.

Supported formats & encodings

Supported languages

ru-RU, en-US, kk-KZ (Kazakh), ky-KG (Kyrgyz), uz-UZ (Uzbek).

Workflow

• Identify input files — from user request.
• Read API key from host environment.
• Run transcription — execute salute_transcribe.py with uv and appropriate arguments.
• Deliver results — present to user human-readable transcript with timestamps to the user and give a direct link to files.

Usage

uv run --with requests {baseDir}/salute_transcribe.py \
  --file /path/to/audio.mp3 \
  --output_dir ~/.openclaw/workspace/transcriptions \
  --lang ru-RU

Arguments

Content-Type mapping

When the file extension doesn't match audio/mpeg, adjust content_type in the script or add logic. Current default is audio/mpeg (MP3). For .wav files use audio/wav, etc.

Output files

For input file meetingABC.mp3 the script produces:

Output text format

[00:01 - 00:20]:
Ну, даже если сосредоточиться на идее узкой щели.

[00:20 - 00:45]:
Следующий фрагмент текста здесь.

Notes

• Token is valid for ~30 minutes; the script fetches a new one each run.
• Large files (>1 hour) may need --max-wait-time increased beyond 300s.
• The callcenter model is optimized for telephony audio (8kHz, mono).
• Profanity filter is disabled by default (enable_profanity_filter=False).
• The script uses normalized text by default (numbers as digits, abbreviations expanded). Raw text is also available in the JSON output.